Filling body in-situ strength online prediction system and method based on image and wave velocity

Abstract

The invention provides an image and wave velocity-based filling body in-situ strength online prediction system and method, and belongs to the technical field of mine filling materials, and the system comprises an in-situ filling body strength prediction device, data acquisition equipment and a data analysis unit; the in-situ filling body strength prediction device is used for acquiring an image and an ultrasonic velocity parameter of a mine in-situ filling body and transmitting acquired image data and ultrasonic velocity parameter data to the data acquisition equipment; the data acquisition equipment is used for receiving image data and ultrasonic velocity parameter data and establishing a mechanical information database; and the data analysis unit is used for analyzing the image data and the ultrasonic velocity parameter data in real time according to a pre-established mathematical model to obtain an online prediction result, and performing evaluation and early warning on the online prediction result. According to the system, the testing cost is reduced, real-time continuous in-situ nondestructive testing is realized, and the accuracy of a prediction result is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of mine filling materials, and in particular relates to an online prediction system and method for in-situ strength of a filling body based on images and wave velocity. Background Art

[0002] The backfill mining method uses backfill to support the surrounding rock of the goaf to control ground pressure and ensure the safety of the mining site. Therefore, the backfill must have a certain stability, and the uniaxial compressive strength of the backfill is an important indicator for evaluating its quality and stability.

[0003] At present, there are three main methods for evaluating the strength of filling bodies: indoor tests, non-destructive testing (mainly ultrasonic velocity and resistivity), and on-site core sampling tests. Both indoor tests and non-destructive testing are based on small-sized artificially prepared samples indoors. Although they are highly accurate and easy to operate, they do not consider the size effect, so the measured strength is not in-situ. On-site core sampling tests measure in-situ strength, but the mechanical vibration during the sampling operation will affect the integrity of the sample, so the test results are highly uncertain. Therefore, there is an urgent need for an online accurate prediction system for the strength of in-situ filling bodies.

[0004] Patent CN 114839095 A discloses an in-situ mechanical parameter testing device and method for deep well high-concentration cemented fillings. A portable backpack drill is used to complete the drilling of core samples in the selected test area, and then an in-situ rapid detection uniaxial press is used to perform on-site strength testing on the samples to obtain the uniaxial compressive strength of the filling. This patent uses a portable backpack drill and an in-situ rapid detection uniaxial press. The former does not require external electricity and air ducts and is relatively simple. The latter uses a manual hydraulic pump to provide a pressure source and can measure the strength of the specimen on-site without transportation. However, in-situ core sampling still has problems of construction disturbance and human damage during operation, and the integrity of the sample is poor, which affects the accuracy of the data; at the same time, single-point sampling can only obtain filling strength data of a single age, and continuous monitoring of filling strength has not yet been achieved.

[0005] Patents CN201410483855 and CN201510875789 proposed a monitoring system and detection method for the consolidation and hardening process of cemented fillings. Based on the conclusions of the paper, the conductivity of the filling is measured to monitor the curing process of the filling and predict its strength. Although this method has high accuracy, the measurement results of conductivity will be affected by temperature changes, which in turn affects the strength prediction results.

[0006] In recent years, slag-based binders have been widely used in domestic mines due to their low CO2 emissions, high strength, good corrosion resistance, low hydration heat release, and low cost, and have achieved significant economic and technical benefits. Slag generates blue-green ferrous ion compounds during the hydration process, so its appearance is blue-green.

[0007] Based on the typical characteristic of slag-based filling bodies showing blue-green color, patent CN202310297951.9 proposes an image-based intelligent prediction system and method for the strength of slag-based filling bodies. It mainly establishes a connection between the color and strength of the in-situ filling body through intelligent image processing, and then predicts the strength parameters of the slag-based filling body, so as to achieve the purpose of rapid and accurate in-situ mechanical parameter testing. This method can easily and quickly detect the strength of the filling body, with low cost and high accuracy. However, this patent is a prediction method and does not involve a prediction device. Moreover, this method only predicts based on images, ignoring the important influence of pore structure on strength.

[0008] Patent CN202411468299.3 proposes a high-precision intelligent prediction method for the strength of slag-based fillings that combines color and pore structure characteristics. By establishing the relationship between the color, pore structure characteristics and strength of the slag-based filling, a high-precision intelligent prediction model is constructed using a neural network to predict the strength of the filling. This patent also takes into account the effects of the number of hydration products and pore structure on the strength of the filling, making the prediction results more accurate. However, this patent uses low-field nuclear magnetic resonance testing to obtain the pore structure characteristic values ​​of the filling, and requires coring in the laboratory or on-site to prepare samples, so continuous prediction cannot be achieved; at the same time, the image acquisition device is only suitable for indoor monitoring and cannot be used for on-site filling image acquisition. Summary of the invention

[0009] In view of the shortcomings of the prior art, the present invention provides an online prediction system and method for the in-situ strength of backfill based on images and wave velocity. The system and method mainly use image recognition and ultrasonic wave velocity to respectively characterize the two factors that affect the strength of slag-based backfill, namely the number of hydration products and pore structure. The system and method are used to achieve real-time, continuous and accurate prediction of the in-situ strength of slag-based backfill at mining sites, thus providing a basis for the quality and stability evaluation of mine backfill.

[0010] In the first aspect, the present application proposes an online prediction system for in-situ strength of a filling body based on images and wave velocity, comprising: an in-situ filling body strength prediction device, a data acquisition device and a data analysis unit;

[0011] The in-situ filling body strength prediction device is connected to a data acquisition device, and the data acquisition device is connected to a data analysis unit;

[0012] The in-situ filling body strength prediction device is used to obtain the image and ultrasonic velocity parameters of the in-situ filling body of the mine and transmit the obtained image data and ultrasonic velocity parameter data to the data acquisition device;

[0013] The data acquisition device is used to receive image data and ultrasonic velocity parameter data and establish a mechanical information database;

[0014] The data analysis unit is used to analyze image data and ultrasonic velocity parameter data in real time according to a pre-established mathematical model to obtain online prediction results, and to evaluate and warn the online prediction results. The pre-established mathematical model is trained using a mechanical information database established by a data acquisition device.

[0015] Furthermore, the in-situ filling body strength prediction device includes a device box housing, a sensor and a transmission part. There are multiple sensors installed on the inside or outside of the device box housing, and a motor housing is arranged outside the transmission part.

[0016] Furthermore, the sensor includes: an ultrasonic velocity sensor and an image sensor.

[0017] Furthermore, the device box shell is made of transparent material and is in a cubic shape. Grooves are arranged on three non-adjacent edges. The grooves are used to install the ultrasonic velocity sensor. The ultrasonic velocity sensor is in the shape of a cylinder, and the size of the groove is one-fourth of the cylinder.

[0018] Furthermore, the ultrasonic velocity sensors are three groups of six, which are installed in pairs on three non-adjacent edges outside the shell, with one ultrasonic velocity sensor placed at one end of an edge and another ultrasonic velocity sensor placed at the other end of an edge, and two ultrasonic velocity sensors form a group.

[0019] Furthermore, the transmission part includes: a motor and a cube image sensor bracket, wherein the motor is installed on the outer side of the bottom surface of the device box shell, the cube image sensor bracket is installed on the inner side of the bottom surface of the device box shell, the cube image sensor bracket is connected to the transmission part of the motor, and there is a motor shell outside the motor.

[0020] Furthermore, there are two image sensors, which are respectively installed on the top and side of the cubic image sensor bracket inside the device box shell.

[0021] Furthermore, the data acquisition device is equipped with a colorimetric card, which is arranged on a side of the device box housing where the motor is not installed, and is used for color correction when the image sensor returns image data.

[0022] Furthermore, the data acquisition equipment is equipped with a plurality of in-situ filling body strength prediction devices, and the plurality of in-situ filling body strength prediction devices are connected to one end of a multi-core cable through a wiring terminal, and the other end of the multi-core cable is connected to the data acquisition equipment.

[0023] In the second aspect, the present application proposes an online prediction method for in-situ strength of a filling body based on images and wave velocity, which is implemented by the online prediction system for in-situ strength of a filling body based on images and wave velocity described in the first aspect, and includes:

[0024] Before the online prediction, the in-situ filling body strength prediction device is placed at the predetermined position of the goaf to be filled;

[0025] After the downhole filling process begins, the in-situ filling body strength prediction device will collect the image data and ultrasonic velocity parameter data of the in-situ filling body according to the set data acquisition frequency and transmit them to the data acquisition device;

[0026] The data acquisition device receives the image data and ultrasonic velocity parameter data and establishes a mechanical information database;

[0027] The data analysis unit analyzes the image data and ultrasonic velocity parameter data in real time according to a pre-established mathematical model to obtain an online prediction result, and evaluates and warns the online prediction result. The pre-established mathematical model is trained using a mechanical information database established by a data acquisition device.

[0028] Beneficial effects:

[0029] This application proposes an online prediction system and method for the in-situ strength of filling bodies based on images and wave velocity. It does not require on-site drilling and sampling and sample transportation, and realizes non-destructive testing of filling body strength, reduces testing costs, and improves operability and safety. At the same time, the sensor in the in-situ filling body strength prediction device is connected to the data analysis unit through the data acquisition device, realizing accurate, efficient, real-time and continuous in-situ non-destructive measurement of filling body strength. At the same time, the image and ultrasonic wave velocity parameters of the mine filling body are detected, taking into account the influence of the number of hydration products and pore structure on the filling body strength, and improving the accuracy of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Schematic diagram of the in-situ strength online prediction system of the filling body according to the embodiment of the present invention;

[0031] Figure 2 A schematic diagram of an isometric three-dimensional structure of an in-situ filling body strength prediction device according to an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of the shell structure of an in-situ filling body strength prediction device according to an embodiment of the present invention;

[0033] Figure 4 Schematic diagram of transmission and sensors of an in-situ filling body strength prediction device according to an embodiment of the present invention;

[0034] Figure 5 The transmission device of the in-situ filling body strength prediction device according to the embodiment of the present invention;

[0035] Figure 6 A schematic diagram of the arrangement of an online prediction system for in-situ strength of a filling body according to an embodiment of the present invention;

[0036] Figure 7 Mathematical model diagram of the in-situ strength online prediction system of the filling body according to the embodiment of the present invention;

[0037] Among them: 1-in-situ filling body strength prediction device; 11-equipment box shell; 12-sensor; 121-ultrasonic velocity sensor; 122-image sensor; 13-transmission part; 131-motor; 132-cube image sensor bracket; 14-motor shell; 2-data acquisition equipment; 21-mechanical information database; 22-multi-core cable; 3-data analysis unit; 31-pre-established mathematical model; 4-goaf; 5-mine pillar; 6-filling retaining wall. DETAILED DESCRIPTION

[0038] The specific implementation of the present application is further described in detail below in conjunction with the drawings and examples.

[0039] In the prior art, there are usually the following problems:

[0040] (1) Indoor tests do not take into account the size effect, and the measured strength is not the in-situ strength.

[0041] (2) The integrity of rock samples from on-site coring tests cannot be guaranteed, affecting the accuracy of strength data.

[0042] (3) The strength results obtained in each test are relatively isolated and have no continuity in time.

[0043] (4) The strength prediction results based on conductivity will be affected by temperature and cause deviations.

[0044] (5) It is difficult to guarantee accuracy when strength prediction is performed using only one method.

[0045] (6) The image acquisition device is not suitable for field use.

[0046] The present application proposes an online prediction system and method for the in-situ strength of filling bodies based on images and wave velocity, in which ultrasonic wave velocity sensors and image sensors are used. Ultrasonic wave velocity and image recognition are both non-destructive testing methods for the strength of filling bodies. There is no need to drill samples, thus avoiding the problem of inaccurate strength caused by incomplete samples. At the same time, the data measured by the two methods of ultrasonic wave velocity and image recognition are not affected by other factors such as temperature. The two methods are used for prediction, and the test data is comprehensively considered to improve the accuracy of the final prediction results. In the image acquisition part of the online strength prediction system, a small-sized image sensor is used, which is more suitable for image acquisition in a limited space. The data measured by the sensor is transmitted to the server through a cable, realizing the online continuous prediction of the filling body strength. By placing the online strength prediction system at a predetermined position in the goaf to be filled inside the mine filling body, it is ensured that the obtained strength data is the actual on-site in-situ data, and there is no need to consider the size effect.

[0047] Embodiment 1:

[0048] This embodiment proposes an online prediction system for in-situ strength of filling bodies based on images and wave velocity, such as Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 As shown, it comprises: an in-situ filling body strength prediction device 1, a data acquisition device 2 and a data analysis unit 3;

[0049] The in-situ filling body strength prediction device 1 is connected to a data acquisition device 2, and the data acquisition device 2 is connected to a data analysis unit 3;

[0050] The in-situ filling body strength prediction device 1 is used to obtain the image and ultrasonic velocity parameters of the in-situ filling body of the mine and transmit the obtained image data and ultrasonic velocity parameter data to the data acquisition device 2;

[0051] The data acquisition device 2 is used to receive image data and ultrasonic velocity parameter data and establish a mechanical information database 21;

[0052] The data analysis unit 3 is used to analyze image data and ultrasonic velocity parameter data in real time according to a pre-established mathematical model 31, obtain online prediction results, and evaluate and warn the online prediction results. The pre-established mathematical model 31 is trained using a mechanical information database 21 established by a data acquisition device 2.

[0053] The in-situ filling body strength prediction device 1 comprises a device box housing 11, a sensor 12 and a transmission part 13. There are multiple sensors 12 installed inside or outside the device box housing 11. A motor housing 14 is arranged outside the transmission part 13.

[0054] In this embodiment, the device box housing 11 provides a large installation space for each sensor 12 and the transmission part 13. The ultrasonic velocity sensor 121 can be installed on three non-adjacent edges on the outside of the device box housing to more comprehensively monitor the ultrasonic velocity of the in-situ filling body; the motor 131 of the transmission part 13 can be installed on any side of the device box housing 11 and connected to the cubic image sensor bracket 132 inside the device box housing. At the same time, other sensors with different monitoring functions can be installed at different positions according to different needs to make the detection results more comprehensive.

[0055] Specifically, the device box shell 11 is a closed cube box made of acrylic material with a side length of 14 cm. Depending on the task requirements and the number of sensor types, the side length and shape of the device box are not limited to the above situation. Its side length can be set to 10-60 cm, and the shape can be a rectangular structure or other shape structures.

[0056] The sensor 12 includes an ultrasonic velocity sensor 121 and an image sensor 122 .

[0057] The device box housing 11 is made of transparent material and is in a cubic shape. Grooves are arranged on three non-adjacent edges. The grooves are used to install the ultrasonic velocity sensor 121. The ultrasonic velocity sensor 121 is in a cylindrical shape, and the size of the groove is one-fourth of the cylinder.

[0058] The ultrasonic velocity sensors 121 are arranged in three groups of six and are installed in pairs on three non-adjacent edges of the outer shell. One ultrasonic velocity sensor 121 is placed at one end of an edge and another ultrasonic velocity sensor 121 is placed at the other end of an edge. Two ultrasonic velocity sensors 121 form a group.

[0059] In this embodiment, the ultrasonic velocity sensor 121 can realize the ultrasonic velocity measurement of the in-situ filling body of the mine, reflecting the changes in the pore structure inside the in-situ filling body. The ultrasonic propagation time accuracy of the sensor is 0.1μs, the measurement frequency is 54kHz, and the sensor diameter is 30mm; the image sensor 122 can realize the image acquisition of the mine filling body, with a maximum resolution of 3120*4208 pixels, the photosensitive element and sensor type are CMOS, equipped with a flash to provide lighting means, and supports autofocus.

[0060] The data of the ultrasonic velocity sensor 121 and the image sensor 122 are transmitted to the data acquisition device via the multi-core cable 22 connecting them.

[0061] When there are multiple in-situ filling body strength prediction devices 1 , the multiple in-situ filling body strength prediction devices 1 are connected to one end of a multi-core cable 22 via a wiring terminal, and the other end of the multi-core cable 22 is connected to the data acquisition device 2 .

[0062] The transmission part 13 includes: a motor 131 and a cubic image sensor bracket 132, wherein the motor 131 is installed on the outer side of the bottom surface of the device box shell 11, and the cubic image sensor bracket 132 is installed on the inner side of the bottom surface of the device box shell 11. The cubic image sensor bracket 132 is connected to the transmission part of the motor 131, and a motor shell 14 is provided outside the motor.

[0063] There are two image sensors 122 , which are respectively installed on the top and side of a cubic image sensor bracket 132 inside the device box housing 11 .

[0064] The data acquisition device 2 is equipped with a colorimetric card, which is arranged on a side of the device box housing 11 where the motor 131 is not installed, and is used for color correction when the image sensor 122 returns image data.

[0065] The data acquisition device 2 is equipped with a plurality of in-situ filling body strength prediction devices 1 , which are connected to one end of a multi-core cable 22 via a wiring terminal, and the other end of the multi-core cable 22 is connected to the data acquisition device 2 .

[0066] Embodiment 2:

[0067] This embodiment proposes an online prediction method for in-situ strength of a filling body based on images and wave velocity, which is implemented by using the online prediction system for in-situ strength of a filling body based on images and wave velocity described in Embodiment 1, including:

[0068] Before the online prediction, the in-situ filling body strength prediction device 1 is placed at a predetermined position of the goaf 4 to be filled;

[0069] After the downhole filling process begins, the in-situ filling body strength prediction device 1 will collect image data and ultrasonic velocity parameter data of the in-situ filling body according to the set data acquisition frequency and transmit them to the data acquisition device 2;

[0070] The data acquisition device 2 receives the image data and ultrasonic velocity parameter data and establishes a mechanical information database 21;

[0071] The data analysis unit 3 analyzes the image data and ultrasonic velocity parameter data in real time according to the pre-established mathematical model 31 to obtain online prediction results, and evaluates and warns the online prediction results. The pre-established mathematical model 31 is trained using the mechanical information database 21 established by the data acquisition device 2.

[0072] In this embodiment, the in-situ filling body strength prediction device 1 is placed in advance at a predetermined position of the goaf 4 to be filled; pillars 5 are arranged on both sides of the goaf 4 to support the goaf 4 before the filling body forms strength, control the ground pressure, and ensure the safety of personnel and the stability of the mining site; after the underground filling work is completed, the ultrasonic velocity sensor 121 on the in-situ filling body strength prediction device 1 will perform ultrasonic velocity measurement of the filling body at an interval of 1 time / hour and transmit the data back, the image sensor 122 will reciprocate at a speed of 360° / minute, and take pictures and transmit images when the image sensor 122 is facing any side, and transmit the data to the data acquisition device 2; the data acquisition device 2 establishes a mechanical information database 21; the data analysis unit 3 analyzes and evaluates the various parameters in the mechanical information database 21 in real time and outputs the prediction results in real time.

[0073] Before starting the installation of the underground goaf 4, it is necessary to first check whether the performance of the in-situ filling body strength prediction device 1 and the data acquisition device 2 are working normally.

[0074] Specifically, the in-situ filling body strength prediction device 1 can be adjusted to a predetermined position by a fixed pulley fixed to the top plate of the goaf 4 before the filling work begins. The data acquisition equipment 2 should be installed on the outside of the filling retaining wall 6, and the battery power supply or 220V AC power supply should be selected according to the on-site working conditions.

[0075] Specifically, the predetermined position is set according to the size and shape of the goaf 4, and it should be ensured as much as possible that the in-situ filling body strength prediction device 1 arranged at the predetermined position can collect strength prediction related parameters of various characteristic parts of the filling body.

[0076] In addition, a margin should be left for the multi-core cables 22 of the in-situ filling body strength prediction device when they are laid, and they are prohibited from being intertwined when they are gathered together. After being led out to the outside of the filling retaining wall 6, they are connected to the data acquisition equipment 2, and the excess multi-core cables 22 are rolled up and hung on the steel bars near the data acquisition equipment 2 to prevent them from being damaged by the rolling equipment.

[0077] Specifically, the mathematical model 31 pre-established by the data analysis unit 3 for data processing will be established based on the indoor test data, such as Figure 7 As shown: the curing temperature and humidity are determined according to the actual filling environment of the mine. Taking into account the influence of factors such as settlement during the filling process, specimens with different concentrations and binder contents are prepared using the same material for mine filling and cured at different ages. After the specimens are cured, images and ultrasonic velocities of the specimens are obtained, and the mechanical strength test of the specimens is carried out. The mechanical strength test results are fitted with the images and ultrasonic velocities to obtain a mathematical model.

[0078] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0079] The protection scope of the present application is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. An online prediction system for in-situ strength of filling bodies based on images and wave velocity, characterized in that: include: In-situ filling body strength prediction device (1), data acquisition equipment (2) and data analysis unit (3); The in-situ filling body strength prediction device (1) is connected to a data acquisition device (2), and the data acquisition device (2) is connected to a data analysis unit (3); The in-situ filling body strength prediction device (1) is used to obtain an image and ultrasonic velocity parameters of an in-situ filling body of a mine and transmit the obtained image data and ultrasonic velocity parameter data to the data acquisition device (2); The data acquisition device (2) is used to receive image data and ultrasonic velocity parameter data and establish a mechanical information database (21); The data analysis unit (3) is used to analyze image data and ultrasonic velocity parameter data in real time according to a pre-established mathematical model (31), obtain online prediction results, and evaluate and warn the online prediction results. The pre-established mathematical model (31) is trained using a mechanical information database (21) established by a data acquisition device (2).

2. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 1 is characterized in that: The in-situ filling body strength prediction device (1) comprises a device box housing (11), a sensor (12) and a transmission part (13), wherein a plurality of sensors (12) are installed inside or outside the device box housing (11), and a motor housing (14) is arranged outside the transmission part (13).

3. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 2 is characterized in that: The sensor (12) comprises an ultrasonic velocity sensor (121) and an image sensor (122).

4. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 2 is characterized in that: The device box housing (11) is made of a transparent material and is in the shape of a cube. Grooves are provided on three non-adjacent edges. The grooves are used to install an ultrasonic velocity sensor (121). The ultrasonic velocity sensor (121) is in the shape of a cylinder, and the size of the groove is one-fourth of the cylinder.

5. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 3 is characterized in that: The ultrasonic velocity sensors (121) are composed of three groups of six, which are installed in pairs on three non-adjacent edges outside the shell, with one ultrasonic velocity sensor (121) placed at one end of an edge and another ultrasonic velocity sensor (121) placed at the other end of an edge, and two ultrasonic velocity sensors (121) form a group.

6. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 2 is characterized in that: The transmission part (13) comprises: a motor (131) and a cubic image sensor bracket (132), wherein the motor (131) is mounted on the outside of the bottom surface of the device box housing (11), the cubic image sensor bracket (132) is mounted on the inside of the bottom surface of the device box housing (11), the cubic image sensor bracket (132) is connected to the transmission part of the motor (131), and a motor housing (14) is provided outside the motor.

7. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 3 is characterized in that: There are two image sensors (122), which are respectively mounted on the top and side of a cubic image sensor bracket (132) inside the device box housing (11).

8. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 1 is characterized in that: The data acquisition device (2) is equipped with a colorimetric card, which is arranged on a side of the device box housing (11) where the motor (131) is not installed, and is used for color correction when the image sensor (122) returns image data.

9. The in-situ strength online prediction system for filling bodies based on images and wave velocity according to claim 1 is characterized in that: The data acquisition device (2) is equipped with a plurality of in-situ filling body strength prediction devices (1), the plurality of in-situ filling body strength prediction devices (1) are connected to one end of a multi-core cable (22) via a wiring terminal, and the other end of the multi-core cable (22) is connected to the data acquisition device (2).

10. An online prediction method for in-situ strength of filling body based on image and wave velocity, characterized in that: The in-situ strength online prediction system of filling body based on image and wave velocity according to any one of claims 1 to 9 is implemented, comprising: Before the online prediction, the in-situ filling body strength prediction device (1) is placed at a predetermined position of the goaf to be filled (4); After the downhole filling process begins, the in-situ filling body strength prediction device (1) collects image data and ultrasonic velocity parameter data of the in-situ filling body according to a set data acquisition frequency and transmits the data to the data acquisition device (2); The data acquisition device (2) receives the image data and ultrasonic velocity parameter data and establishes a mechanical information database (21); The data analysis unit (3) analyzes the image data and ultrasonic velocity parameter data in real time according to a pre-established mathematical model (31), obtains an online prediction result, and evaluates and warns the online prediction result. The pre-established mathematical model (31) is trained using a mechanical information database (21) established by a data acquisition device (2).

Images